© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42078
    Prev
    Next
    INDEX
    Explanations

    business rates, harvester instructor, shoot preparation

    np_acts-logits-general · gemini-2.5-flash-lite

    locking, touching, parameters, regularly, until, array

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    0.54
    2
    0.47
    สนับสนุน
    0.47
    平台的
    0.47
    O
    0.46
    of
    0.44
    </b>
    0.43
     системи
    0.42
    绝
    0.42
     о
    0.42
    POSITIVE LOGITS
    ڊ
    0.48
    charges
    0.47
    وندی
    0.46
    зё
    0.46
     लाइ
    0.46
    कार्बन
    0.45
     charging
    0.45
    蜞
    0.44
    φαν
    0.43
    يند
    0.43
    Activations Density 0.000%

    No Known Activations